In this paper new error measures to evaluate image features in three-dimensional scenes are proposed and reviewed. The proposed error measures are designed to take into account feature shapes, and ground truth data can be easily estimated. As other approaches, they are not error-free and a quantitative evaluation is given according to the number of wrong matches and mismatches in order to assess their validit
We quantitatively analyze the rendering quality of image-based rendering (IBR) algorithms using per-...
In this paper a suitable methodology for the improvement of the reliability of results in classifica...
The error in three-dimensional (3-D) scans by a 3-D measurement system based upon fringe projection ...
In this paper new error measures to evaluate image features in three-dimensional scenes are proposed...
This paper presents a new framework to evaluate feature descriptors on 3D datasets. The proposed met...
In this paper a suitable methodology for the improvement of the reliability of results in classifica...
Basic concepts in probability are employed to develop analytic formulae for both the expectation (bi...
An important objective in the evaluation of algorithms with sensory inputs is the development of mea...
In this paper we present three error measures based on feature perception models, in which pixel err...
U-V disparity is a technique that is commonly used to detect obstacles in 3D scenes, modeling them a...
We characterize the precision of a 3-D reconstruction from stereo: we derive confidence intervals fo...
[[abstract]]To develop a reliable computer vision system, the employed algorithm must guarantee good...
In this thesis, we present two new methods to overcome the effects of both camera calibration errors...
Abstract-With the increased popularity of 3D videos online and through consumer and cinema media, th...
In the context of virtual and augmented reality, computer vision plays a pivotal role. To benchmark ...
We quantitatively analyze the rendering quality of image-based rendering (IBR) algorithms using per-...
In this paper a suitable methodology for the improvement of the reliability of results in classifica...
The error in three-dimensional (3-D) scans by a 3-D measurement system based upon fringe projection ...
In this paper new error measures to evaluate image features in three-dimensional scenes are proposed...
This paper presents a new framework to evaluate feature descriptors on 3D datasets. The proposed met...
In this paper a suitable methodology for the improvement of the reliability of results in classifica...
Basic concepts in probability are employed to develop analytic formulae for both the expectation (bi...
An important objective in the evaluation of algorithms with sensory inputs is the development of mea...
In this paper we present three error measures based on feature perception models, in which pixel err...
U-V disparity is a technique that is commonly used to detect obstacles in 3D scenes, modeling them a...
We characterize the precision of a 3-D reconstruction from stereo: we derive confidence intervals fo...
[[abstract]]To develop a reliable computer vision system, the employed algorithm must guarantee good...
In this thesis, we present two new methods to overcome the effects of both camera calibration errors...
Abstract-With the increased popularity of 3D videos online and through consumer and cinema media, th...
In the context of virtual and augmented reality, computer vision plays a pivotal role. To benchmark ...
We quantitatively analyze the rendering quality of image-based rendering (IBR) algorithms using per-...
In this paper a suitable methodology for the improvement of the reliability of results in classifica...
The error in three-dimensional (3-D) scans by a 3-D measurement system based upon fringe projection ...